Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Urban solid waste incineration process nitrogen oxide soft measurement method based on modular neural network

A neural network and nitrogen oxide technology, applied in biological neural network models, character and pattern recognition, complex mathematical operations, etc., can solve problems such as changing furnace conditions and difficulty in establishing a soft sensor model with a single neural network, and achieve improved The effect of precision

Pending Publication Date: 2021-04-30
BEIJING UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The incineration process of municipal solid waste involves complex physical and chemical reactions. The NOx concentration is related to many process variables such as the composition of the waste entering the furnace, the temperature in the furnace, and the air volume. Moreover, the working conditions in the furnace are changeable during the incineration process, and it is difficult to establish an accurate software with a single neural network. measurement model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Urban solid waste incineration process nitrogen oxide soft measurement method based on modular neural network
  • Urban solid waste incineration process nitrogen oxide soft measurement method based on modular neural network
  • Urban solid waste incineration process nitrogen oxide soft measurement method based on modular neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The simulation experiment in this paper is divided into two parts. Firstly, the benchmark experiment (sinE function fitting) is used to verify the performance of the modular neural network model, and then the actual data of the MSWI factory is used to conduct industrial experiments on the model. By comparing with the existing methods, it reflects the effectiveness of the proposed algorithm.

[0069] Combining the selection results of the mRMR algorithm with the mechanism of solid waste incineration, 20 features are finally determined in this paper, as shown in Table 2.

[0070] Table 2 Feature selection results

[0071]

[0072]

[0073] After mRMR algorithm feature selection, combined with the solid waste incineration mechanism, NOx emissions are considered from two parts: generation and elimination. From the analysis of the generation process, it is mainly related to temperature and air volume. Considering the elimination process, it is mainly related to the inj...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an urban solid waste incineration process nitrogen oxide soft measurement method based on a modular neural network, and belongs to the field of solid waste treatment. The emission of NOx can be effectively controlled through real-time detection of toxic gas-nitrogen oxide (NOx) generated in MSWI. In an industrial field, a high-precision instrument-flue gas emission continuous monitoring system is adopted to detect the NOx concentration in flue gas emission, the measurement result is greatly influenced by the environment, and the equipment maintenance cost is high. The method comprises the steps that firstly, task decomposition is conducted through a fuzzy c-means algorithm, and a task is decomposed into different sub-tasks; secondly,for different sub-tasks, soft measurement sub-models designed by adopting a radial basis function neural network, and a nonlinear relationship between a characteristic variable and NOx is established; and finally, sub-network output is integrated through the cascaded neural network. The effectiveness of the proposed method is verified by adopting a reference experiment and actual data of a certain MSWI factory.

Description

technical field [0001] The invention belongs to the field of solid waste treatment. Background technique [0002] With the development of social economy and the continuous improvement of people's living standards, municipal solid waste (Municipal solid wastes, MSW) is increasing at a global annual growth rate of 8%, which has a great impact on the ecological environment. MSW incineration (MSWincineration, MSWI) is one of the more commonly used solid waste treatment methods at present. It can not only achieve solid waste volume reduction, but also "turn waste into treasure". Nitrogen oxides (NOx, mainly including NO and NO 2 ) is one of the typical emissions in MSWI tail gas, and it is also the main component of environmental pollution. The NOx concentration in my country's MSWI tail gas is higher than that of some EU countries. Therefore, it is particularly important to reduce NOx emissions in MSWI tail gas. At present, the main method of controlling NOx emissions is to r...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/02G06F17/16
CPCG06N3/02G06F17/16G06F18/23G06F18/214
Inventor 乔俊飞段滈杉蒙西汤健
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products